Related papers: Empowering Multilevel DSMLs with Integrated Runtim…
In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typically apply formal…
Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are…
Rational verification is the problem of determining which temporal logic properties will hold in a multi-agent system, under the assumption that agents in the system act rationally, by choosing strategies that collectively form a…
Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements have utilized large language models (LLMs) to automate this modeling process. However,…
Test-time reinforcement learning (TTRL) has emerged as a promising paradigm for self-evolving large reasoning models (LRMs), enabling online adaptation on unlabeled test inputs via self-induced rewards through majority voting. However, a…
We advocate that simulation based on offline profiling is a promising approach to better understand and improve the complex ML systems. Our approach uses operation-level profiling and dataflow based simulation to ensure it offers a unified…
Offline runtime verification involves the static analysis of executions of a system against a specification. For distributed systems, it is generally not possible to characterize executions in the form of global traces, given the absence of…
Even if the verification of authentication protocols can be achieved by means of formal analysis, the modelling of such an activity is an error-prone task due to the lack of automated and integrated processes. This paper proposes a…
Hyperproperties extend trace properties to express properties of sets of traces, and they are increasingly popular in specifying various security and performance-related properties in domains such as cyber-physical systems, smart grids, and…
The reasoning capabilities of large language models (LLMs) have been significantly improved through reinforcement learning (RL). Nevertheless, LLMs still struggle to consistently verify their own reasoning traces. This raises the research…
Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectories may still rely on incomplete derivations, weak evidence, or statements that…
Automation systems exist in many variants and may evolve over time in order to deal with different environment contexts or to fulfill changing customer requirements. This induces an increased complexity during design-time as well as tedious…
In industrial model-based development (MBD) frameworks, requirements are typically specified informally using textual descriptions. To enable the application of formal methods, these specifications need to be formalized in the input…
This paper presents a novel approach to e-commerce payment fraud detection by integrating reinforcement learning (RL) with Large Language Models (LLMs). By framing transaction risk as a multi-step Markov Decision Process (MDP), RL optimizes…
The development and application of formal methods is a long standing research topic within the field of computer science. One particular challenge that remains is the uptake of formal methods into industrial practices. This paper introduces…
Designing correct replicated data types (RDTs) is challenging because replicas evolve independently and must be merged while preserving application intent. A promising approach is correct-by-construction development in a proof-oriented…
Multimodal Large Language Models (MLLMs) have achieved impressive performances in mathematical reasoning, yet they remain vulnerable to visual hallucinations and logical inconsistencies that standard outcome-based supervision fails to…
Validating Large Language Models with ReLM explores the application of formal languages to evaluate and control Large Language Models (LLMs) for memorization, bias, and zero-shot performance. Current approaches for evaluating these types…
Recent studies show LLMs struggle with complex instructions involving multiple constraints (e.g., length, format, sentiment). Existing works address this issue by fine-tuning, which heavily relies on fine-tuning data quality and is…
Due to the increasing usage of machine learning (ML) techniques in security- and safety-critical domains, such as autonomous systems and medical diagnosis, ensuring correct behavior of ML systems, especially for different corner cases, is…